This paper proposes an innovative method based on AI, to reinforce traceability systems in detecting possible counterfeiting by product substitution. It is an item-based mass balance method that analyses the agreement of the traceability data flows not by using explicit (even stochastic) rules, but by exploiting the learning capabilities of a neural network. The system can then detect suspect information in a traceability data flow. The AI-based method was applied to a pork slaughtering and meat cutting chain case study, and used the weights of different cuts of a pork carcase as the training phase of AI. Any analogous carcase information along the supply line might indicate substitution or modification of the pork carcase cuts.
Read the full open access paper